Deep Dehazing Powered by Image Processing Network

Image processing is a very fundamental technique in the field of low-level vision. However, with the development of deep learning over the past five years, most low-level vision methods tend to ignore this technique. Recent dehazing methods also refrain from using conventional image processing techn...

Full description

Saved in:
Bibliographic Details
Published in2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) pp. 1209 - 1218
Main Authors Kim, Guisik, Park, Jinhee, Kwon, Junseok
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2023
Subjects
Artificial neural networks
Computer architecture
Computer vision
Conferences
Deep learning
Focusing
Learning systems
Online AccessGet full text

Cover

More Information
Summary:Image processing is a very fundamental technique in the field of low-level vision. However, with the development of deep learning over the past five years, most low-level vision methods tend to ignore this technique. Recent dehazing methods also refrain from using conventional image processing techniques, whereas only focusing on the development of new deep neural network (DNN) architectures. Unlike this recent trend, we show that image processing techniques are still competitive, if they are incorporated into DNNs. In this paper, we utilize conventional image processing techniques (i.e. curve adjustment, retinex decomposition, and multiple image fusion) for accurate dehazing. Moreover, we employ direct learning for stable dehazing performance. The proposed method can perform with low computational cost and easy to learn. The experimental results demonstrate that the proposed method produces accurate dehazing results compared to recent algorithms.
ISSN:2160-7516
DOI:10.1109/CVPRW59228.2023.00128